Learning descriptors for object recognition and 3D pose estimation
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3109-3118
- https://doi.org/10.1109/cvpr.2015.7298930
Abstract
Detecting poorly textured objects and estimating their 3D pose reliably is still a very challenging problem. We introduce a simple but powerful approach to computing descriptors for object views that efficiently capture both the object identity and 3D pose. By contrast with previous manifold-based approaches, we can rely on the Euclidean distance to evaluate the similarity between descriptors, and therefore use scalable Nearest Neighbor search methods to efficiently handle a large number of objects under a large range of poses. To achieve this, we train a Convolutional Neural Network to compute these descriptors by enforcing simple similarity and dissimilarity constraints between the descriptors. We show that our constraints nicely untangle the images from different objects and different views into clusters that are not only well-separated but also structured as the corresponding sets of poses: The Euclidean distance between descriptors is large when the descriptors are from different objects, and directly related to the distance between the poses when the descriptors are from the same object. These important properties allow us to outperform state-of-the-art object views representations on challenging RGB and RGB-D data.Keywords
Other Versions
This publication has 27 references indexed in Scilit:
- Scalable Nearest Neighbor Algorithms for High Dimensional DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Boosting masked dominant orientation templates for efficient object detectionComputer Vision and Image Understanding, 2014
- Fast Exact Search in Hamming Space With Multi-Index HashingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Fast, Accurate Detection of 100,000 Object Classes on a Single MachinePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- A Survey of Manifold Learning for ImagesIPSJ Transactions on Computer Vision and Applications, 2009
- Scalable Recognition with a Vocabulary TreePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Learning a Similarity Metric Discriminatively, with Application to Face VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Real-time focus range sensorIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Mental rotation and orientation-dependence in shape recognitionCognitive Psychology, 1989